activity
20182021
most citedSubstructure Substitution: Structured Data Augmentation for NLP

3 citations · 3 across the 1 of their papers we have counts for

collaborators

6 papers

cs.CL20213 cited

Substructure Substitution: Structured Data Augmentation for NLP

Haoyue Shi, Karen Livescu, Kevin Gimpel

We study a family of data augmentation methods, substructure substitution (SUB2), for natural language processing (NLP) tasks. SUB2 generates new examples by substituting substruct…

cs.CL2020

On the Role of Supervision in Unsupervised Constituency Parsing

Haoyue Shi, Karen Livescu, Kevin Gimpel

We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing score on the Wall Street Journal (WSJ) development set (1,700…

cs.CL2020

A Cross-Task Analysis of Text Span Representations

Shubham Toshniwal, Haoyue Shi, Bowen Shi +3

Many natural language processing (NLP) tasks involve reasoning with textual spans, including question answering, entity recognition, and coreference resolution. While extensive res…

cs.CL2019

Visually Grounded Neural Syntax Acquisition

Haoyue Shi, Jiayuan Mao, Kevin Gimpel +1

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an approach for learning syntactic representations and structures without any explicit supervision. The model learn…

cs.CL2018

On Tree-Based Neural Sentence Modeling

Haoyue Shi, Hao Zhou, Jiaze Chen +1

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the expl…

cs.CL2018

Learning Visually-Grounded Semantics from Contrastive Adversarial Samples

Haoyue Shi, Jiayuan Mao, Tete Xiao +2

We study the problem of grounding distributional representations of texts on the visual domain, namely visual-semantic embeddings (VSE for short). Begin with an insightful adversar…